%config Completer.use_jedi = True

conda install kagglehub

Retrieving notices: done
Note: you may need to restart the kernel to use updated packages.

Channels:
 - defaults
Platform: win-64
Collecting package metadata (repodata.json): ...working... done
Solving environment: ...working... done

# All requested packages already installed.

import kagglehub  #descargar dataset
import pandas as pd #procesos de tabla
import numpy as np  #procesos de vectores y matemáticas

#visualizacion
import plotly.express as px
import matplotlib.pyplot as plt
import seaborn as sns
from scipy.stats import norm

# Download latest version
path = kagglehub.dataset_download("ruchi798/data-science-job-salaries")

print("Path to dataset files:", path)

Warning: Looks like you're using an outdated `kagglehub` version, please consider updating (latest version: 0.3.10)
Path to dataset files: C:\Users\darly\.cache\kagglehub\datasets\ruchi798\data-science-job-salaries\versions\1

data= pd.DataFrame({
    "nombres": ["ana", "juana", "sara"],
    "edad": [12,23,34]
})
data

data2= pd.DataFrame({
    "nombres": ["ana", "juana", "sara"],
    "salario": [120,230,340]
})
data2

new_df= data.merge(data2)

new_df

df = pd.read_csv("C:/Users/darly/.cache/kagglehub/datasets/ruchi798/data-science-job-salaries/versions/1/ds_salaries.csv") #forma 1

df = pd.read_csv(r"C:\Users\darly\.cache\kagglehub\datasets\ruchi798\data-science-job-salaries\versions\1\ds_salaries.csv") #forma 2

df.head()

df.tail()

df.describe()

df.columns

Index(['Unnamed: 0', 'work_year', 'experience_level', 'employment_type',
       'job_title', 'salary', 'salary_currency', 'salary_in_usd',
       'employee_residence', 'remote_ratio', 'company_location',
       'company_size'],
      dtype='object')

df[df.salary_in_usd > 250000]

df[df.salary_in_usd > 250000].describe()

df.job_title

0                  Data Scientist
1      Machine Learning Scientist
2               Big Data Engineer
3            Product Data Analyst
4       Machine Learning Engineer
                  ...            
602                 Data Engineer
603                 Data Engineer
604                  Data Analyst
605                  Data Analyst
606                  AI Scientist
Name: job_title, Length: 607, dtype: object

df.query("job_title == 'Data Scientist'") #RECUERDE QUE LA CONSULTA QUERY DEBE SER DENTRO DE UNA CADENA

df.iloc[20:40]

df[["job_title", "salary"]]

df.iloc[:, [2,4,5]]

df.iloc[10:40, [2,4,5]]

df.loc[:,"experience_level": "job_title"]

df.loc[df["experience_level"]== "MI"]

df.loc[df["experience_level"]== "MI", ["job_title",	"salary"]]

df.loc[df["experience_level"]== "MI", ["job_title",	"salary"]].sort_values("salary", ascending=True)

df.rename(columns= {"salary": "salario"})

df.drop(columns={"salary"})

df["salario en pesos"] = df.salary * 4500
df

df.sample(frac=0.5) #fragmento deel 50 por ciento de los datos

df.sample(n=100) #numero determinado de muestras

df.groupby("job_title").mean(numeric_only=True)

df.groupby("job_title").mean(numeric_only=True).count() #cuenta

Unnamed: 0          50
work_year           50
salary              50
salary_in_usd       50
remote_ratio        50
salario en pesos    50
dtype: int64

df.groupby("job_title").agg({
    "salary": ["max", "mean"]
})  #agrupar por una columan y determinadas medidas

df.shape #tamaño de data

(607, 13)

df.nunique()

Unnamed: 0            607
work_year               3
experience_level        4
employment_type         4
job_title              50
salary                272
salary_currency        17
salary_in_usd         369
employee_residence     57
remote_ratio            3
company_location       50
company_size            3
salario en pesos      272
dtype: int64

df.count() #contar datos

Unnamed: 0            607
work_year             607
experience_level      607
employment_type       607
job_title             607
salary                607
salary_currency       607
salary_in_usd         607
employee_residence    607
remote_ratio          607
company_location      607
company_size          607
salario en pesos      607
dtype: int64

df.isnull().sum() #que datos son nulos

Unnamed: 0            0
work_year             0
experience_level      0
employment_type       0
job_title             0
salary                0
salary_currency       0
salary_in_usd         0
employee_residence    0
remote_ratio          0
company_location      0
company_size          0
salario en pesos      0
dtype: int64

top10_job_title = df['job_title'].value_counts()[:10] #las primeras 10 empleos mas comunes

fig = px.bar(y=top10_job_title.values, 
             x=top10_job_title.index, 
             color = top10_job_title.index,
             color_discrete_sequence=px.colors.sequential.PuBuGn,
             text=top10_job_title.values,
             title= '2.1.2. Top 10 Job Titles',
             template= 'plotly_dark')
fig.show()

fig.update_layout(
    xaxis_title="Job Titles",
    yaxis_title="count",
    font = dict(size=17,family="Franklin Gothic"))
fig.show()

df_cuant= df.select_dtypes(include=['int64', 'float64'])
df_cuant

df_cuant= df_cuant.iloc[:, 1:]

df_cuant

for i in range(1, df_cuant.shape[1]):
    plt.figure(figsize=(8, 4))  # Crear una nueva figura para cada gráfico
    
    plt.plot(df_cuant.work_year, df_cuant.iloc[:, i], marker="o", linestyle="",color="green", label=df_cuant.columns[i])
    
    # Personalización del gráfico
    plt.xlabel("año de trabajo")
    plt.ylabel(df_cuant.columns[i])
    plt.title(f"Evolución de {df_cuant.columns[i]}")
    plt.legend()
    plt.grid(True)
    
    plt.show()  # Mostrar cada gráf

df_cuant= df_cuant.iloc[:,1:]
df_cuant

# Graficar cada variable numérica con su campana de Gauss
for columna in df_cuant.columns:
    plt.figure(figsize=(8, 5))  # Nueva figura para cada variable
    
    # Histograma con densidad
    sns.histplot(df_cuant[columna], kde=True, bins=20, stat="density", color="blue", label="Datos")

    # Ajuste de la curva normal teórica
    media = df_cuant[columna].mean()
    desviacion = df_cuant[columna].std()
    x = np.linspace(df_cuant[columna].min(), df_cuant[columna].max(), 100) #linea de ahuste de la cuerva
    y = norm.pdf(x, media, desviacion)
    plt.plot(x, y, color="red", label="Campana de Gauss")

    # Personalización del gráfico
    plt.title(f"Distribución de {columna}")
    plt.xlabel(columna)
    plt.ylabel("Densidad")
    plt.legend()
    plt.grid(True)

    plt.show()  # Muestra cada gráfico individualmente

correlacion = df_cuant.corr()

correlacion

correlacion = df_cuant.corr()
# 🔹 Crear el mapa de calor
plt.figure(figsize=(10, 6))  # Ajustar tamaño de la figura
sns.heatmap(correlacion, annot=True, cmap="coolwarm", fmt=".2f", linewidths=0.5)

# 🔹 Título del gráfico
plt.title("Matriz de Correlación")

# 🔹 Mostrar el gráfico
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

# 🔹 Seleccionar solo las columnas numéricas del DataFrame


# 🔹 Crear un boxplot para todas las columnas numéricas
plt.figure(figsize=(12,6))  # Tamaño del gráfico
sns.boxplot(df_cuant)

# 🔹 Mejorar visualización
plt.xticks(rotation=45)  # Rotar nombres de variables
plt.title("Diagramas de caja de todas las variables numéricas")

# 🔹 Mostrar gráfico
plt.show()

# 🔹 Recorrer cada columna numérica y hacer un boxplot individual
for i in range(1, df_cuant.shape[1]):
    plt.figure(figsize=(6,4))  # Tamaño de cada gráfico
    sns.boxplot(x=df_cuant.iloc[:, i])
    plt.title(f"Distribución de {df_cuant.columns[i]}")  # Título con el nombre de la variable
    plt.show()

df_cuant.describe()

plt.figure(figsize=(12,6))
sns.heatmap(df.isnull(), cmap="viridis", cbar=False, yticklabels=False)
plt.title("Mapa de calor de valores nulos")
plt.show()

plt.figure(figsize=(12,6))
sns.heatmap(df_cuant.isnull(), cmap="viridis", cbar=False, yticklabels=False)
plt.title("Mapa de calor de valores nulos")
plt.show()

# Contar cuántos registros hay por año
conteo_años = df["work_year"].value_counts()
print(conteo_años)

# Crear el gráfico de torta
plt.figure(figsize=(8,8))
plt.pie(conteo_años, labels=conteo_años.index, autopct="%1.1f%%", colors=plt.cm.Paired.colors)

# Título y mostrar gráfico
plt.title("Distribución de registros por Año")
plt.show()

work_year
2022    318
2021    217
2020     72
Name: count, dtype: int64

df["experiencia_num"]= df["experience_level"].replace({'EN': 1, 'MI': 2, 'SE': 3, 'EX': 4})
df

C:\Users\darly\AppData\Local\Temp\ipykernel_21952\4027909897.py:1: FutureWarning:

Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`

df["tamanio_campania"]= df["company_size"].replace({'S': 1, 'M': 2, 'L': 3})
df

C:\Users\darly\AppData\Local\Temp\ipykernel_21952\911041496.py:1: FutureWarning:

Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`

df.columns

Index(['Unnamed: 0', 'work_year', 'experience_level', 'employment_type',
       'job_title', 'salary', 'salary_currency', 'salary_in_usd',
       'employee_residence', 'remote_ratio', 'company_location',
       'company_size', 'salario en pesos', 'experiencia_num',
       'tamanio_campania'],
      dtype='object')

df= df.drop(columns=["Unnamed: 0", "salario en pesos"], inplace=False) #eliminar columna mal nombrada, y creada
df

df_analisis= df.select_dtypes(include=['int64', 'float64'])
df_analisis

correlacion = df_analisis.corr()
# 🔹 Crear el mapa de calor
plt.figure(figsize=(10, 6))  # Ajustar tamaño de la figura
sns.heatmap(correlacion, annot=True, cmap="coolwarm", fmt=".2f", linewidths=0.5)

# 🔹 Título del gráfico
plt.title("Matriz de Correlación")

# 🔹 Mostrar el gráfico
plt.show()

df['job_title'].nunique() #saca suma de unicos

50

job_uni= list(df['job_title'].unique()) #una lista de los valores unicos 
job_uni

['Data Scientist',
 'Machine Learning Scientist',
 'Big Data Engineer',
 'Product Data Analyst',
 'Machine Learning Engineer',
 'Data Analyst',
 'Lead Data Scientist',
 'Business Data Analyst',
 'Lead Data Engineer',
 'Lead Data Analyst',
 'Data Engineer',
 'Data Science Consultant',
 'BI Data Analyst',
 'Director of Data Science',
 'Research Scientist',
 'Machine Learning Manager',
 'Data Engineering Manager',
 'Machine Learning Infrastructure Engineer',
 'ML Engineer',
 'AI Scientist',
 'Computer Vision Engineer',
 'Principal Data Scientist',
 'Data Science Manager',
 'Head of Data',
 '3D Computer Vision Researcher',
 'Data Analytics Engineer',
 'Applied Data Scientist',
 'Marketing Data Analyst',
 'Cloud Data Engineer',
 'Financial Data Analyst',
 'Computer Vision Software Engineer',
 'Director of Data Engineering',
 'Data Science Engineer',
 'Principal Data Engineer',
 'Machine Learning Developer',
 'Applied Machine Learning Scientist',
 'Data Analytics Manager',
 'Head of Data Science',
 'Data Specialist',
 'Data Architect',
 'Finance Data Analyst',
 'Principal Data Analyst',
 'Big Data Architect',
 'Staff Data Scientist',
 'Analytics Engineer',
 'ETL Developer',
 'Head of Machine Learning',
 'NLP Engineer',
 'Lead Machine Learning Engineer',
 'Data Analytics Lead']

#un diccionario con los datos unicos y su respectivo valor
dict_job= {}
for i in range(df['job_title'].nunique()):
    dict_job[job_uni[i]]=i+1 

dict_job

{'Data Scientist': 1,
 'Machine Learning Scientist': 2,
 'Big Data Engineer': 3,
 'Product Data Analyst': 4,
 'Machine Learning Engineer': 5,
 'Data Analyst': 6,
 'Lead Data Scientist': 7,
 'Business Data Analyst': 8,
 'Lead Data Engineer': 9,
 'Lead Data Analyst': 10,
 'Data Engineer': 11,
 'Data Science Consultant': 12,
 'BI Data Analyst': 13,
 'Director of Data Science': 14,
 'Research Scientist': 15,
 'Machine Learning Manager': 16,
 'Data Engineering Manager': 17,
 'Machine Learning Infrastructure Engineer': 18,
 'ML Engineer': 19,
 'AI Scientist': 20,
 'Computer Vision Engineer': 21,
 'Principal Data Scientist': 22,
 'Data Science Manager': 23,
 'Head of Data': 24,
 '3D Computer Vision Researcher': 25,
 'Data Analytics Engineer': 26,
 'Applied Data Scientist': 27,
 'Marketing Data Analyst': 28,
 'Cloud Data Engineer': 29,
 'Financial Data Analyst': 30,
 'Computer Vision Software Engineer': 31,
 'Director of Data Engineering': 32,
 'Data Science Engineer': 33,
 'Principal Data Engineer': 34,
 'Machine Learning Developer': 35,
 'Applied Machine Learning Scientist': 36,
 'Data Analytics Manager': 37,
 'Head of Data Science': 38,
 'Data Specialist': 39,
 'Data Architect': 40,
 'Finance Data Analyst': 41,
 'Principal Data Analyst': 42,
 'Big Data Architect': 43,
 'Staff Data Scientist': 44,
 'Analytics Engineer': 45,
 'ETL Developer': 46,
 'Head of Machine Learning': 47,
 'NLP Engineer': 48,
 'Lead Machine Learning Engineer': 49,
 'Data Analytics Lead': 50}

df["index_job"]= df['job_title'].replace(dict_job)
df

C:\Users\darly\AppData\Local\Temp\ipykernel_21952\2832190827.py:1: FutureWarning:

Downcasting behavior in `replace` is deprecated and will be removed in a future version. To retain the old behavior, explicitly call `result.infer_objects(copy=False)`. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting', True)`

df

df_analisis = df.select_dtypes(include=['int64', 'float64'])

df_analisis

correlacion = df_analisis.corr()
# 🔹 Crear el mapa de calor
plt.figure(figsize=(10, 6))  # Ajustar tamaño de la figura
sns.heatmap(correlacion, annot=True, cmap="coolwarm", fmt=".2f", linewidths=0.5)

# 🔹 Título del gráfico
plt.title("Matriz de Correlación")

# 🔹 Mostrar el gráfico
plt.show()

df.to_csv(r"C:\Users\darly\OneDrive\Escritorio\materialClaseIA\dataSalarios\dataGeneral.csv", index=False)  # index=False evita guardar los índices
df_analisis.to_csv(r"C:\Users\darly\OneDrive\Escritorio\materialClaseIA\dataSalarios\datosCuantitativos.csv", index=False)  # index=False evita guardar los índices

#librerias para modelos de machine learning
from sklearn.model_selection import train_test_split   #divide la data en entrenamiento y prueba
from sklearn.linear_model import LinearRegression      #apicar modelo de regresion lineal
from sklearn.metrics import mean_squared_error, r2_score # metricas del modelo

# Seleccionar la variable independiente (X) y la dependiente (y)
X = df[["experiencia_num"]] # Variable predictora, doble corchete para que retorno data frame y entre en el modelo
y = df['salary_in_usd']  # Variable objetivo da una serie

X

y

0       79833
1      260000
2      109024
3       20000
4      150000
        ...  
602    154000
603    126000
604    129000
605    150000
606    200000
Name: salary_in_usd, Length: 607, dtype: int64

# se usa para fijar la semilla del generador aleatorio, asegurando que los resultados sean reproducibles.
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

X_train, X_test, y_train, y_test

(     experiencia_num
 9                  3
 227                2
 591                3
 516                3
 132                2
 ..               ...
 71                 2
 106                2
 270                1
 435                2
 102                2
 
 [485 rows x 1 columns],
      experiencia_num
 563                3
 289                3
 76                 2
 78                 2
 182                2
 ..               ...
 249                3
 365                3
 453                2
 548                3
 235                2
 
 [122 rows x 1 columns],
 9      125000
 227     88654
 591    144854
 516    152500
 132     38400
         ...  
 71      42197
 106    187442
 270     72500
 435     91614
 102     36259
 Name: salary_in_usd, Length: 485, dtype: int64,
 563    140250
 289    135000
 76     100000
 78     270000
 182     26005
         ...  
 249    170000
 365    138600
 453    120000
 548     99050
 235    110000
 Name: salary_in_usd, Length: 122, dtype: int64)

# Crear el modelo
modelo1 = LinearRegression()

# Entrenar el modelo con los datos de entrenamiento
modelo1.fit(X_train, y_train)

LinearRegression()

LinearRegression()

# Obtener la pendiente (coeficiente) y la intersección con el eje Y
pendiente =    modelo1.coef_[0]
interseccion = modelo1.intercept_

print(f"Ecuación de la regresión: Salario = {pendiente:.2f} * Experiencia + {interseccion:.2f}") #2f se redolndea a dos flotantes

Ecuación de la regresión: Salario = 44575.96 * Experiencia + 6897.15

# Predecir los salarios en el conjunto de prueba, lo
y_pred_1 = modelo1.predict(X_test)

y_pred_1

array([140625.04456583, 140625.04456583,  96049.08062684,  96049.08062684,
        96049.08062684,  96049.08062684,  51473.11668785,  51473.11668785,
        96049.08062684,  51473.11668785,  96049.08062684, 140625.04456583,
       140625.04456583,  96049.08062684, 140625.04456583, 140625.04456583,
        96049.08062684,  96049.08062684,  51473.11668785, 140625.04456583,
       140625.04456583,  96049.08062684, 140625.04456583,  96049.08062684,
        96049.08062684,  96049.08062684, 140625.04456583,  96049.08062684,
       140625.04456583,  96049.08062684,  51473.11668785, 140625.04456583,
       140625.04456583,  51473.11668785,  96049.08062684, 140625.04456583,
        96049.08062684, 140625.04456583,  51473.11668785, 140625.04456583,
       140625.04456583, 140625.04456583, 140625.04456583, 140625.04456583,
       140625.04456583,  96049.08062684,  96049.08062684,  96049.08062684,
        96049.08062684, 140625.04456583, 140625.04456583,  96049.08062684,
        96049.08062684, 140625.04456583, 140625.04456583, 140625.04456583,
       140625.04456583, 185201.00850483,  51473.11668785, 140625.04456583,
        96049.08062684,  51473.11668785,  96049.08062684, 140625.04456583,
       140625.04456583,  96049.08062684, 140625.04456583,  96049.08062684,
       140625.04456583,  96049.08062684, 140625.04456583,  96049.08062684,
       140625.04456583,  51473.11668785, 140625.04456583, 140625.04456583,
       140625.04456583, 140625.04456583,  96049.08062684, 140625.04456583,
       140625.04456583,  51473.11668785,  96049.08062684,  96049.08062684,
       185201.00850483, 185201.00850483,  51473.11668785, 140625.04456583,
        96049.08062684, 140625.04456583,  96049.08062684,  96049.08062684,
        96049.08062684,  96049.08062684, 140625.04456583,  51473.11668785,
        51473.11668785,  96049.08062684,  96049.08062684, 140625.04456583,
        96049.08062684, 140625.04456583, 140625.04456583, 185201.00850483,
       140625.04456583,  51473.11668785, 140625.04456583, 140625.04456583,
       140625.04456583,  96049.08062684,  96049.08062684,  96049.08062684,
       140625.04456583, 140625.04456583,  51473.11668785,  96049.08062684,
        96049.08062684, 140625.04456583, 140625.04456583,  96049.08062684,
       140625.04456583,  96049.08062684])

# Crear un DataFrame con los valores reales y las predicciones
resultados_predicciones = pd.DataFrame({
    "Salario en USD REAL (y_test)": y_test,
    "Predicción Regresión Lineal ": y_pred_1,
   
})

# Imprimir los primeros valores en formato de tabla
print(resultados_predicciones)  # Muestra solo las primeras filas

     Salario en USD REAL (y_test)  Predicción Regresión Lineal 
563                        140250                 140625.044566
289                        135000                 140625.044566
76                         100000                  96049.080627
78                         270000                  96049.080627
182                         26005                  96049.080627
..                            ...                           ...
249                        170000                 140625.044566
365                        138600                 140625.044566
453                        120000                  96049.080627
548                         99050                 140625.044566
235                        110000                  96049.080627

[122 rows x 2 columns]

# Crear gráfico de dispersión para comparar valores reales y predicciones
plt.figure(figsize=(15,9 ))

# Graficar valores reales (y_test) en azul
plt.scatter(X_test, y_test, color='blue', label="Salario usd Real (y_test)", alpha=0.4)# alpha puntos transperantes

# Graficar predicciones de Regresión Lineal en rojo
plt.scatter(X_test, y_pred_1, color='red', label="Predicción Regresión Lineal", alpha=0.4)

# Configurar el gráfico
plt.xlabel("Nivel experiencia", fontsize=12)
plt.ylabel("Salario USD", fontsize=12)
plt.title("Comparación de Salarios Reales vs Predichos", fontsize=14)
plt.legend()
plt.grid(True, linestyle="--", alpha=0.8)

# Mostrar gráfico
plt.show()

# Calcular el error cuadrático medio (MSE)
mse = mean_squared_error(y_test, y_pred_1)

# Calcular el coeficiente de determinación R^2
r2 = r2_score(y_test, y_pred_1)

print(f"Error cuadrático medio (MSE): {mse:.2f}")
print(f"Coeficiente de determinación (R²): {r2:.2f}")

Error cuadrático medio (MSE): 3019758135.07
Coeficiente de determinación (R²): 0.21

# Calcular el mínimo y máximo de y_test
min_y_test = y_test.min()
max_y_test = y_test.max()

# Calcular el rango de y_test
rango_y_test = max_y_test - min_y_test

# Calcular la desviación estándar de y_test
std_y_test= y_test.std()

#raiz cuadrada de MSE= RMSE
rmse=np.sqrt(mse)


# Mostrar los resultados

print(f"Rango de y_test: {rango_y_test:.2f}")
print(f"Desviación estándar de y_test: {std_y_test:.2f}")
print(f"Raíz de (MSE): (RMSE): {rmse:.2f}")

Rango de y_test: 409141.00
Desviación estándar de y_test: 62163.04
Raíz de (MSE): (RMSE): 54952.33

# Crear gráfico de dispersión
plt.scatter(X_test, y_test, color='blue', label="Datos Reales")
plt.plot(X_test, y_pred_1, color='red', linewidth=2, label="Regresión Lineal")

# Etiquetas
plt.xlabel("Experiencia (en niveles)")
plt.ylabel("Salario en USD")
plt.title("Regresión Lineal: Experiencia vs Salario")
plt.legend()

# Mostrar gráfico
plt.show()

#importar libreria
from sklearn.preprocessing import OneHotEncoder

encoder = OneHotEncoder(handle_unknown='ignore', sparse_output=False)

#transformar los datos  a oneHot
encoded_columns = encoder.fit_transform(df[['job_title']])

encoded_columns

array([[0., 0., 0., ..., 0., 0., 0.],
       [0., 0., 0., ..., 0., 0., 0.],
       [0., 0., 0., ..., 0., 0., 0.],
       ...,
       [0., 0., 0., ..., 0., 0., 0.],
       [0., 0., 0., ..., 0., 0., 0.],
       [0., 1., 0., ..., 0., 0., 0.]])

#crear un dataFrame con la codificación
data_encode= pd.DataFrame(encoded_columns)
data_encode

#convertir en un dataframe pero asignarle nombres a las columnas
data_encode= pd.DataFrame(encoded_columns,columns=encoder.get_feature_names_out(['job_title']))

data_encode

df_analisis

# Combinar datos procesados
df_final = pd.concat([data_encode,df_analisis],axis=1)
df_final

cor=df_final.corr()
cor

# 🔹 Crear el mapa de calor
plt.figure(figsize=(80, 60))  # Ajustar tamaño de la figura
sns.heatmap(cor, annot=True, cmap="coolwarm", fmt=".2f", linewidths=0.5)

# 🔹 Título del gráfico
plt.title("Matriz de Correlación")

# 🔹 Mostrar el gráfico
plt.show()

# Separar variables predictoras y objetivo
X = df_final.drop(columns=['salary_in_usd'])
y = df_final['salary_in_usd']

# Dividir en entrenamiento y prueba
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# elegir modelo
modelo2 = LinearRegression()
# Entrenar modelos
modelo2.fit(X_train, y_train)

LinearRegression()

LinearRegression()

# Hacer predicciones
y_pred_2 = modelo2.predict(X_test)

# Evaluar modelos
mse = mean_squared_error(y_test, y_pred_2)
r2 = r2_score(y_test, y_pred_2)

# Calcular el mínimo y máximo de y_test
min_y_test = y_test.min()
max_y_test = y_test.max()

# Calcular el rango de y_test
rango_y_test = max_y_test - min_y_test

# Calcular la desviación estándar de y_test
std_y_test= y_test.std()

#raiz cuadrada de MSE= RMSE
rmse=np.sqrt(mse)

# Mostrar los resultados

print(f"Rango de y_test: {rango_y_test:.2f}")
print(f"Desviación estándar de y_test: {std_y_test:.2f}")
print(f"Raíz de (MSE): (RMSE): {rmse:.2f}")
print(f"Coeficiente de determinación (R²): {r2:.2f}")

Rango de y_test: 409141.00
Desviación estándar de y_test: 62163.04
Raíz de (MSE): (RMSE): 61377.97
Coeficiente de determinación (R²): 0.02

#crear objeto de encoder, transformar los datos y pasarlos al dataFrame
encoder = OneHotEncoder(handle_unknown='ignore', sparse_output=False)
encoded_columns = encoder.fit_transform(df[['company_location']])
data_encode2= pd.DataFrame(encoded_columns,columns=encoder.get_feature_names_out(['company_location']))
data_encode2

#unir las datas de analisis y la de codificación
df_final = pd.concat([data_encode2,df_analisis],axis=1)

#obtener correlación y gráficarlo
cor=df_final.corr()

# 🔹 Crear el mapa de calor
plt.figure(figsize=(60, 40))  # Ajustar tamaño de la figura
sns.heatmap(cor, annot=True, cmap="coolwarm", fmt=".2f", linewidths=0.5)

# 🔹 Título del gráfico
plt.title("Matriz de Correlación")

# 🔹 Mostrar el gráfico
plt.show()

# Separar variables predictoras y objetivo
X = df_final.drop(columns=['salary_in_usd'])
y = df_final['salary_in_usd']
df_final

# Dividir en entrenamiento y prueba
X_train_3, X_test_3, y_train_3, y_test_3 = train_test_split(X, y, test_size=0.2, random_state=42)

#elegir modelo
modelo3 = LinearRegression()
# Entrenar modelos
modelo3.fit(X_train_3, y_train_3)

LinearRegression()

LinearRegression()

# Hacer predicciones
y_pred_3 = modelo3.predict(X_test_3)

# Evaluar modelos
mse_3 = mean_squared_error(y_test_3, y_pred_3)
r2_3 = r2_score(y_test_3, y_pred_3)

# Calcular el mínimo y máximo de y_test
min_y_test_3 = y_test_3.min()
max_y_test_3 = y_test_3.max()

# Calcular el rango de y_test
rango_y_test_3 = max_y_test_3 - min_y_test_3

# Calcular la desviación estándar de y_test
std_y_test_3= y_test_3.std()

#raiz cuadrada de MSE= RMSE
rmse_3=np.sqrt(mse_3)

# Mostrar los resultados

print(f"Rango de y_test: {rango_y_test_3:.2f}")
print(f"Desviación estándar de y_test: {std_y_test_3:.2f}")
print(f"Raíz de (MSE): (RMSE): {rmse_3:.2f}")
print(f"Coeficiente de determinación (R²): {r2_3:.2f}")

Rango de y_test: 409141.00
Desviación estándar de y_test: 62163.04
Raíz de (MSE): (RMSE): 48970.17
Coeficiente de determinación (R²): 0.37

# Crear un DataFrame con los valores reales y las predicciones
resultados_predicciones = pd.DataFrame({
    "Salario en USD REAL (y_test_3)": y_test_3,
    "Predicción Regresión Lineal model 3 ": y_pred_3,
   
})

# Imprimir los primeros valores en formato de tabla
print(resultados_predicciones)  # Muestra solo las primeras filas

     Salario en USD REAL (y_test_3)  Predicción Regresión Lineal model 3 
563                          140250                         151792.695731
289                          135000                         151822.531968
76                           100000                         125616.675281
78                           270000                         147996.035022
182                           26005                         141707.886136
..                              ...                                   ...
249                          170000                         184347.347725
365                          138600                         142403.356931
453                          120000                          96690.080029
548                           99050                         147327.481202
235                          110000                         131171.794970

[122 rows x 2 columns]

import matplotlib.pyplot as plt

plt.figure(figsize=(10, 6))

# Graficar cada punto (valor real vs predicho)
plt.scatter(range(len(y_test_3)), y_test_3, color='blue', label="Valores Reales", alpha=0.5)
plt.scatter(range(len(y_pred_3)), y_pred_3, color='red', label="Valores Predichos", alpha=0.5)

# Configurar el gráfico
plt.xlabel("Índice de Observación", fontsize=12)
plt.ylabel("Valores de Y", fontsize=12)
plt.title("Comparación entre Valores Reales y Predicciones", fontsize=14)
plt.legend()
plt.grid(True, linestyle="--", alpha=0.5)

# Mostrar gráfico
plt.show()

conda install joblib

Retrieving notices: done
Channels:
 - defaults
Platform: win-64
Collecting package metadata (repodata.json): ...working... done
Solving environment: ...working... done

# All requested packages already installed.


Note: you may need to restart the kernel to use updated packages.

# importar librería
import joblib

# Guardar el modelo 1
joblib.dump(modelo1, 'modelo_entrenado_columnaExperienciaSC.pkl')

['modelo_entrenado_columnaExperienciaSC.pkl']

# Guardar el modelo 3, porque el 2 no merece
joblib.dump(modelo3, 'modelo3_RegMUl_encodeCompany.pkl')

['modelo3_RegMUl_encodeCompany.pkl']

#unir las data final (codificac¿da) y la codificación de job_tittle
df_final_1 = pd.concat([df_final,data_encode],axis=1)

df_final_1

for i in df_final_1.columns:
    print(i)

company_location_AE
company_location_AS
company_location_AT
company_location_AU
company_location_BE
company_location_BR
company_location_CA
company_location_CH
company_location_CL
company_location_CN
company_location_CO
company_location_CZ
company_location_DE
company_location_DK
company_location_DZ
company_location_EE
company_location_ES
company_location_FR
company_location_GB
company_location_GR
company_location_HN
company_location_HR
company_location_HU
company_location_IE
company_location_IL
company_location_IN
company_location_IQ
company_location_IR
company_location_IT
company_location_JP
company_location_KE
company_location_LU
company_location_MD
company_location_MT
company_location_MX
company_location_MY
company_location_NG
company_location_NL
company_location_NZ
company_location_PK
company_location_PL
company_location_PT
company_location_RO
company_location_RU
company_location_SG
company_location_SI
company_location_TR
company_location_UA
company_location_US
company_location_VN
work_year
salary
salary_in_usd
remote_ratio
experiencia_num
tamanio_campania
index_job
job_title_3D Computer Vision Researcher
job_title_AI Scientist
job_title_Analytics Engineer
job_title_Applied Data Scientist
job_title_Applied Machine Learning Scientist
job_title_BI Data Analyst
job_title_Big Data Architect
job_title_Big Data Engineer
job_title_Business Data Analyst
job_title_Cloud Data Engineer
job_title_Computer Vision Engineer
job_title_Computer Vision Software Engineer
job_title_Data Analyst
job_title_Data Analytics Engineer
job_title_Data Analytics Lead
job_title_Data Analytics Manager
job_title_Data Architect
job_title_Data Engineer
job_title_Data Engineering Manager
job_title_Data Science Consultant
job_title_Data Science Engineer
job_title_Data Science Manager
job_title_Data Scientist
job_title_Data Specialist
job_title_Director of Data Engineering
job_title_Director of Data Science
job_title_ETL Developer
job_title_Finance Data Analyst
job_title_Financial Data Analyst
job_title_Head of Data
job_title_Head of Data Science
job_title_Head of Machine Learning
job_title_Lead Data Analyst
job_title_Lead Data Engineer
job_title_Lead Data Scientist
job_title_Lead Machine Learning Engineer
job_title_ML Engineer
job_title_Machine Learning Developer
job_title_Machine Learning Engineer
job_title_Machine Learning Infrastructure Engineer
job_title_Machine Learning Manager
job_title_Machine Learning Scientist
job_title_Marketing Data Analyst
job_title_NLP Engineer
job_title_Principal Data Analyst
job_title_Principal Data Engineer
job_title_Principal Data Scientist
job_title_Product Data Analyst
job_title_Research Scientist
job_title_Staff Data Scientist

df.columns #colu de la data oficial

Index(['work_year', 'experience_level', 'employment_type', 'job_title',
       'salary', 'salary_currency', 'salary_in_usd', 'employee_residence',
       'remote_ratio', 'company_location', 'company_size', 'experiencia_num',
       'tamanio_campania', 'index_job'],
      dtype='object')

df['employment_type_numeric'] = df['employment_type'].map({'FL': 1, 'CT': 2, 'PT': 3, 'FT': 4})
df['remote_ratio_numeric'] = df['remote_ratio'] / 100

#label encode para tipo empleo
df_final_1["tipo_empleo"]= df['employment_type'].map({'FL': 1, 'CT': 2, 'PT': 3, 'FT': 4})

df_final_1.shape

(607, 108)

#transformar datos en intervalor de 0 a 1, 
df_final_1['remote_ratio']

0        0
1        0
2       50
3        0
4       50
      ... 
602    100
603    100
604      0
605    100
606    100
Name: remote_ratio, Length: 607, dtype: int64

df_final_1['remote_ratio_numeric'] = df['remote_ratio'] / 100

df_final_1.shape

(607, 109)

df_final_1.drop(columns=['remote_ratio', 'index_job'], inplace=True)

df_final_1.shape

(607, 107)

# Separar variables predictoras y objetivo
X = df_final_1.drop(columns=['salary_in_usd'])
y = df_final_1['salary_in_usd']

# Dividir en entrenamiento y prueba
X_train_4, X_test_4, y_train_4, y_test_4 = train_test_split(X, y, test_size=0.2, random_state=42)

#elegir modelo
modelo4 = LinearRegression()
# Entrenar modelos
modelo4.fit(X_train_4, y_train_4)

LinearRegression()

LinearRegression()

# Hacer predicciones
y_pred_4 = modelo4.predict(X_test_4)

# Evaluar modelos
mse_4 = mean_squared_error(y_test_4, y_pred_4)
r2_4 = r2_score(y_test_4, y_pred_4)

# Calcular el mínimo y máximo de y_test
min_y_test_4 = y_test_4.min()
max_y_test_4 = y_test_4.max()

# Calcular el rango de y_test
rango_y_test_4 = max_y_test_4 - min_y_test_4

# Calcular la desviación estándar de y_test
std_y_test_4= y_test_4.std()

#raiz cuadrada de MSE= RMSE
rmse_4=np.sqrt(mse_4)

# Mostrar los resultados

print(f"Rango de y_test: {rango_y_test_4:.2f}")
print(f"Desviación estándar de y_test: {std_y_test_4:.2f}")
print(f"Raíz de (MSE): (RMSE): {rmse_4:.2f}")
print(f"Coeficiente de determinación (R²): {r2_4:.2f}")

Rango de y_test: 409141.00
Desviación estándar de y_test: 62163.04
Raíz de (MSE): (RMSE): 47710.45
Coeficiente de determinación (R²): 0.41

#mirar puntos
import matplotlib.pyplot as plt

plt.figure(figsize=(10, 6))

# Graficar cada punto (valor real vs predicho)
plt.scatter(range(len(y_test_4)), y_test_4, color='blue', label="Valores Reales", alpha=0.5)
plt.scatter(range(len(y_pred_4)), y_pred_4, color='red', label="Valores Predichos", alpha=0.5)

# Configurar el gráfico
plt.xlabel("Índice de Observación", fontsize=12)
plt.ylabel("Valores de Y", fontsize=12)
plt.title("Comparación entre Valores Reales y Predicciones", fontsize=14)
plt.legend()
plt.grid(True, linestyle="--", alpha=0.5)

# Mostrar gráfico
plt.show()

#guardar modelo 4

joblib.dump(modelo4, 'RMultiple_datTrasns.pkl')

['RMultiple_datTrasns.pkl']

#guardadarData
df_final_1.to_csv("dataSalarios_final.csv", index=False)  # index=False evita guardar los índices

# Filtrar outliers en salario usando IQR
Q1, Q3 = df_final_1['salary_in_usd'].quantile([0.25, 0.75])
IQR = Q3 - Q1
df_final_1 = df_final_1[(df_final_1['salary_in_usd'] >= (Q1 - 1.5 * IQR)) & (df_final_1['salary_in_usd'] <= (Q3 + 1.5 * IQR))]

df_final_1.shape

(597, 107)

# Separar variables predictoras y objetivo
X = df_final_1.drop(columns=['salary_in_usd'])
y = df_final_1['salary_in_usd']

# Dividir en entrenamiento y prueba
X_train_5, X_test_5, y_train_5, y_test_5 = train_test_split(X, y, test_size=0.2, random_state=42)

#elegir modelo
modelo5 = LinearRegression()
# Entrenar modelos
modelo5.fit(X_train_5, y_train_5)

LinearRegression()

LinearRegression()

# Hacer predicciones
y_pred_5 = modelo5.predict(X_test_5)

# Evaluar modelos
mse_5 = mean_squared_error(y_test_5, y_pred_5)
r2_5 = r2_score(y_test_5, y_pred_5)

# Calcular el mínimo y máximo de y_test
min_y_test_5 = y_test_5.min()
max_y_test_5 = y_test_5.max()

# Calcular el rango de y_test
rango_y_test_5 = max_y_test_5 - min_y_test_5

# Calcular la desviación estándar de y_test
std_y_test_5= y_test_5.std()

#raiz cuadrada de MSE= RMSE
rmse_5=np.sqrt(mse_5)

# Mostrar los resultados

print(f"Rango de y_test: {rango_y_test_5:.2f}")
print(f"Desviación estándar de y_test: {std_y_test_5:.2f}")
print(f"Raíz de (MSE): (RMSE): {rmse_5:.2f}")
print(f"Coeficiente de determinación (R²): {r2_5:.2f}")

Rango de y_test: 270118.00
Desviación estándar de y_test: 51826.73
Raíz de (MSE): (RMSE): 40044.95
Coeficiente de determinación (R²): 0.40

#mirar puntos
import matplotlib.pyplot as plt

plt.figure(figsize=(10, 6))

# Graficar cada punto (valor real vs predicho)
plt.scatter(range(len(y_test_5)), y_test_5, color='blue', label="Valores Reales", alpha=0.5)
plt.scatter(range(len(y_pred_5)), y_pred_5, color='red', label="Valores Predichos", alpha=0.5)



# Configurar el gráfico
plt.xlabel("Índice de Observación", fontsize=12)
plt.ylabel("Valores de Y", fontsize=12)
plt.title("Comparación entre Valores Reales y Predicciones", fontsize=14)
plt.legend()
plt.grid(True, linestyle="--", alpha=0.5)

# Mostrar gráfico
plt.show()

#guardar modelo 5

joblib.dump(modelo5, 'RMultiple_outliner.pkl')

['RMultiple_outliner.pkl']

#guardar la Data
df_final_1.to_csv("dataSalarios_final_outliner.csv", index=False)  # index=False evita guardar los índices

Vamos a probar arboles de decision con las dos datas

# Entrenar modelos de randoms forest

from sklearn.ensemble import RandomForestRegressor

modelo_rf1 = RandomForestRegressor(n_estimators=100, random_state=42) #la data final con outliner
modelo_rf2 = RandomForestRegressor(n_estimators=100, random_state=42) #la data final sin outliner

modelo_rf1.fit(X_train_4, y_train_4)
modelo_rf2.fit(X_train_5, y_train_5)

# Hacer predicciones
y_pred_rf1 = modelo_rf1.predict(X_test_4)
y_pred_rf2 = modelo_rf2.predict(X_test_5)

# Evaluar modelos
mse_rf1 = mean_squared_error(y_test_4, y_pred_rf1)
r2_rf1 = r2_score(y_test_4, y_pred_rf1)
mse_rf2 = mean_squared_error(y_test_5, y_pred_rf2)
r2_rf2 = r2_score(y_test_5, y_pred_rf2)

# Comparación de modelos
comparacion_modelos = pd.DataFrame({
    "Modelo": ["Random forest 1", "Random Forest 2"],
    "MSE": [mse_rf1, mse_rf2],
    "R²": [r2_rf1, r2_rf2]
})

# Mostrar comparación
print(comparacion_modelos)

            Modelo           MSE        R²
0  Random forest 1  6.047060e+08  0.842219
1  Random Forest 2  2.375971e+08  0.910799

#guardar los modelos
joblib.dump(modelo_rf1, 'RanForest_conOutliner.pkl')
joblib.dump(modelo_rf2, 'RanForest_SinOutliner.pkl')

['RanForest_SinOutliner.pkl']

#mirar puntos
import matplotlib.pyplot as plt

plt.figure(figsize=(10, 6))

# Graficar cada punto (valor real vs predicho)
plt.scatter(range(len(y_test_4)), y_test_4, color='blue', label="Valores Reales", alpha=0.5)
plt.scatter(range(len(y_pred_rf1)), y_pred_rf1, color='red', label="Valores Predichos", alpha=0.5)



# Configurar el gráfico
plt.xlabel("Índice de Observación", fontsize=12)
plt.ylabel("Valores de Y", fontsize=12)
plt.title("Comparación entre Valores Reales y Predicciones", fontsize=14)
plt.legend()
plt.grid(True, linestyle="--", alpha=0.5)

# Mostrar gráfico
plt.show()

#mirar puntos
import matplotlib.pyplot as plt

plt.figure(figsize=(10, 6))

# Graficar cada punto (valor real vs predicho)
plt.scatter(range(len(y_test_5)), y_test_5, color='blue', label="Valores Reales", alpha=0.5)
plt.scatter(range(len(y_pred_rf2)), y_pred_rf2, color='red', label="Valores Predichos", alpha=0.5)



# Configurar el gráfico
plt.xlabel("Índice de Observación", fontsize=12)
plt.ylabel("Valores de Y", fontsize=12)
plt.title("Comparación entre Valores Reales y Predicciones", fontsize=14)
plt.legend()
plt.grid(True, linestyle="--", alpha=0.5)

# Mostrar gráfico
plt.show()

	Unnamed: 0	work_year	salary	salary_in_usd	remote_ratio
count	607.000000	607.000000	6.070000e+02	607.000000	607.00000
mean	303.000000	2021.405272	3.240001e+05	112297.869852	70.92257
std	175.370085	0.692133	1.544357e+06	70957.259411	40.70913
min	0.000000	2020.000000	4.000000e+03	2859.000000	0.00000
25%	151.500000	2021.000000	7.000000e+04	62726.000000	50.00000
50%	303.000000	2022.000000	1.150000e+05	101570.000000	100.00000
75%	454.500000	2022.000000	1.650000e+05	150000.000000	100.00000
max	606.000000	2022.000000	3.040000e+07	600000.000000	100.00000

	Unnamed: 0	work_year	salary	salary_in_usd	remote_ratio
count	16.00000	16.000000	16.000000	16.000000	16.000000
mean	233.06250	2021.062500	360837.500000	360837.500000	78.125000
std	197.70364	0.771902	97733.221066	97733.221066	40.697051
min	1.00000	2020.000000	256000.000000	256000.000000	0.000000
25%	74.25000	2020.750000	269100.000000	269100.000000	87.500000
50%	191.00000	2021.000000	352500.000000	352500.000000	100.000000
75%	432.50000	2022.000000	417750.000000	417750.000000	100.000000
max	534.00000	2022.000000	600000.000000	600000.000000	100.000000

	Unnamed: 0	work_year	salary	salary_in_usd	remote_ratio	salario en pesos
job_title
3D Computer Vision Researcher	77.000000	2021.000000	4.000000e+05	5409.000000	50.000000	1.800000e+09
AI Scientist	254.142857	2021.142857	2.905714e+05	66135.571429	78.571429	1.307571e+09
Analytics Engineer	458.250000	2022.000000	1.750000e+05	175000.000000	50.000000	7.875000e+08
Applied Data Scientist	351.600000	2021.600000	1.724000e+05	175655.000000	70.000000	7.758000e+08
Applied Machine Learning Scientist	321.000000	2021.500000	1.413500e+05	142068.750000	87.500000	6.360750e+08
BI Data Analyst	106.333333	2020.833333	1.902045e+06	74755.166667	66.666667	8.559204e+09
Big Data Architect	255.000000	2021.000000	1.250000e+05	99703.000000	50.000000	5.625000e+08
Big Data Engineer	123.125000	2020.625000	4.550000e+05	51974.000000	50.000000	2.047500e+09
Business Data Analyst	256.800000	2021.000000	3.550000e+05	76691.200000	90.000000	1.597500e+09
Cloud Data Engineer	122.000000	2021.000000	1.400000e+05	124647.000000	75.000000	6.300000e+08
Computer Vision Engineer	274.833333	2021.166667	8.350000e+04	44419.333333	58.333333	3.757500e+08
Computer Vision Software Engineer	235.666667	2021.333333	1.003333e+05	105248.666667	100.000000	4.515000e+08
Data Analyst	362.010309	2021.680412	9.660496e+04	92893.061856	75.257732	4.347223e+08
Data Analytics Engineer	216.750000	2021.250000	6.175000e+04	64799.250000	75.000000	2.778750e+08
Data Analytics Lead	523.000000	2022.000000	4.050000e+05	405000.000000	100.000000	1.822500e+09
Data Analytics Manager	366.285714	2021.571429	1.271343e+05	127134.285714	85.714286	5.721043e+08
Data Architect	390.636364	2021.727273	1.778739e+05	177873.909091	100.000000	8.004326e+08
Data Engineer	343.537879	2021.590909	1.792106e+05	112725.000000	75.000000	8.064475e+08
Data Engineering Manager	107.200000	2020.600000	1.197998e+05	123227.200000	70.000000	5.390991e+08
Data Science Consultant	138.000000	2020.714286	1.227143e+05	69420.714286	71.428571	5.522143e+08
Data Science Engineer	229.666667	2021.333333	8.450000e+04	75803.333333	83.333333	3.802500e+08
Data Science Manager	274.000000	2021.333333	1.062599e+06	158328.500000	83.333333	4.781694e+09
Data Scientist	314.832168	2021.391608	5.083472e+05	108187.832168	63.986014	2.287562e+09
Data Specialist	165.000000	2021.000000	1.650000e+05	165000.000000	100.000000	7.425000e+08
Director of Data Engineering	171.500000	2021.000000	1.412500e+05	156738.000000	100.000000	6.356250e+08
Director of Data Science	185.857143	2021.000000	1.932857e+05	195074.000000	42.857143	8.697857e+08
ETL Developer	373.500000	2022.000000	5.000000e+04	54957.000000	0.000000	2.250000e+08
Finance Data Analyst	183.000000	2021.000000	4.500000e+04	61896.000000	50.000000	2.025000e+08
Financial Data Analyst	279.000000	2021.500000	2.750000e+05	275000.000000	75.000000	1.237500e+09
Head of Data	302.200000	2021.400000	1.564000e+05	160162.600000	90.000000	7.038000e+08
Head of Data Science	270.250000	2021.500000	1.467188e+05	146718.750000	50.000000	6.602344e+08
Head of Machine Learning	384.000000	2022.000000	6.000000e+06	79039.000000	50.000000	2.700000e+10
Lead Data Analyst	64.333333	2020.666667	5.690000e+05	92203.000000	100.000000	2.560500e+09
Lead Data Engineer	145.500000	2020.833333	1.403333e+05	139724.500000	66.666667	6.315000e+08
Lead Data Scientist	53.000000	2020.333333	1.101667e+06	115190.000000	50.000000	4.957500e+09
Lead Machine Learning Engineer	457.000000	2022.000000	8.000000e+04	87932.000000	0.000000	3.600000e+08
ML Engineer	179.333333	2021.000000	2.676667e+06	117504.000000	83.333333	1.204500e+10
Machine Learning Developer	358.000000	2021.666667	1.000000e+05	85860.666667	83.333333	4.500000e+08
Machine Learning Engineer	288.585366	2021.317073	2.727179e+05	104880.146341	67.073171	1.227230e+09
Machine Learning Infrastructure Engineer	234.333333	2021.000000	9.733333e+04	101145.000000	50.000000	4.380000e+08
Machine Learning Manager	29.000000	2020.000000	1.570000e+05	117104.000000	50.000000	7.065000e+08
Machine Learning Scientist	248.000000	2021.250000	1.584125e+05	158412.500000	68.750000	7.128562e+08
Marketing Data Analyst	90.000000	2021.000000	7.500000e+04	88654.000000	100.000000	3.375000e+08
NLP Engineer	455.000000	2022.000000	2.400000e+05	37236.000000	50.000000	1.080000e+09
Principal Data Analyst	370.000000	2021.500000	1.225000e+05	122500.000000	100.000000	5.512500e+08
Principal Data Engineer	196.000000	2021.000000	3.283333e+05	328333.333333	100.000000	1.477500e+09
Principal Data Scientist	205.285714	2021.000000	2.067143e+05	215242.428571	85.714286	9.302143e+08
Product Data Analyst	12.000000	2020.000000	2.350000e+05	13036.000000	50.000000	1.057500e+09
Research Scientist	246.562500	2021.125000	1.104937e+05	109019.500000	53.125000	4.972216e+08
Staff Data Scientist	283.000000	2021.000000	1.050000e+05	105000.000000	100.000000	4.725000e+08

	salary
	max	mean
job_title
3D Computer Vision Researcher	400000	4.000000e+05
AI Scientist	1335000	2.905714e+05
Analytics Engineer	205300	1.750000e+05
Applied Data Scientist	380000	1.724000e+05
Applied Machine Learning Scientist	423000	1.413500e+05
BI Data Analyst	11000000	1.902045e+06
Big Data Architect	125000	1.250000e+05
Big Data Engineer	1672000	4.550000e+05
Business Data Analyst	1400000	3.550000e+05
Cloud Data Engineer	160000	1.400000e+05
Computer Vision Engineer	180000	8.350000e+04
Computer Vision Software Engineer	150000	1.003333e+05
Data Analyst	450000	9.660496e+04
Data Analytics Engineer	110000	6.175000e+04
Data Analytics Lead	405000	4.050000e+05
Data Analytics Manager	150260	1.271343e+05
Data Architect	266400	1.778739e+05
Data Engineer	4450000	1.792106e+05
Data Engineering Manager	174000	1.197998e+05
Data Science Consultant	423000	1.227143e+05
Data Science Engineer	159500	8.450000e+04
Data Science Manager	7000000	1.062599e+06
Data Scientist	30400000	5.083472e+05
Data Specialist	165000	1.650000e+05
Director of Data Engineering	200000	1.412500e+05
Director of Data Science	325000	1.932857e+05
ETL Developer	50000	5.000000e+04
Finance Data Analyst	45000	4.500000e+04
Financial Data Analyst	450000	2.750000e+05
Head of Data	235000	1.564000e+05
Head of Data Science	224000	1.467188e+05
Head of Machine Learning	6000000	6.000000e+06
Lead Data Analyst	1450000	5.690000e+05
Lead Data Engineer	276000	1.403333e+05
Lead Data Scientist	3000000	1.101667e+06
Lead Machine Learning Engineer	80000	8.000000e+04
ML Engineer	8500000	2.676667e+06
Machine Learning Developer	100000	1.000000e+05
Machine Learning Engineer	4900000	2.727179e+05
Machine Learning Infrastructure Engineer	195000	9.733333e+04
Machine Learning Manager	157000	1.570000e+05
Machine Learning Scientist	260000	1.584125e+05
Marketing Data Analyst	75000	7.500000e+04
NLP Engineer	240000	2.400000e+05
Principal Data Analyst	170000	1.225000e+05
Principal Data Engineer	600000	3.283333e+05
Principal Data Scientist	416000	2.067143e+05
Product Data Analyst	450000	2.350000e+05
Research Scientist	450000	1.104937e+05
Staff Data Scientist	105000	1.050000e+05

	salary	salary_in_usd	remote_ratio	salario en pesos
salary	1.000000	-0.083906	-0.014608	1.000000
salary_in_usd	-0.083906	1.000000	0.132122	-0.083906
remote_ratio	-0.014608	0.132122	1.000000	-0.014608
salario en pesos	1.000000	-0.083906	-0.014608	1.000000

configuración del entorno¶

Obtener dataset¶

exploración, filtro y limpieza de la data¶

Visualizacion de la data a partir de gráficos¶

Últimas Exploraciones de la data para aplicar modelos¶

Guardar las diversas datas¶

Dividir data¶

Aplicar un modelo¶

Cuando entrenamos un modelo de Regresión Lineal con sklearn, el modelo encuentra una ecuación de la recta en la forma:¶

Calificar un modelo¶

Interpretación¶

reestructurar data¶

one Hot encoding¶

aplicar regresión lineal múltiple¶

Probar otras características¶

Gráficar y_pred y y_test¶

Guardar modelos¶

Transformar el resto de datos, unirlos a la data de entrenamiento y probar modelo¶

probar el modelo de regresión lineal multiple¶

eliminar valores atipicos¶

Arboles de decisión¶

Random forest¶

interpretación¶

	Unnamed: 0	work_year	experience_level	employment_type	job_title	salary	salary_currency	salary_in_usd	employee_residence	remote_ratio	company_location	company_size
0	0	2020	MI	FT	Data Scientist	70000	EUR	79833	DE	0	DE	L
1	1	2020	SE	FT	Machine Learning Scientist	260000	USD	260000	JP	0	JP	S
2	2	2020	SE	FT	Big Data Engineer	85000	GBP	109024	GB	50	GB	M
3	3	2020	MI	FT	Product Data Analyst	20000	USD	20000	HN	0	HN	S
4	4	2020	SE	FT	Machine Learning Engineer	150000	USD	150000	US	50	US	L

	Unnamed: 0	work_year	experience_level	employment_type	job_title	salary	salary_currency	salary_in_usd	employee_residence	remote_ratio	company_location	company_size
602	602	2022	SE	FT	Data Engineer	154000	USD	154000	US	100	US	M
603	603	2022	SE	FT	Data Engineer	126000	USD	126000	US	100	US	M
604	604	2022	SE	FT	Data Analyst	129000	USD	129000	US	0	US	M
605	605	2022	SE	FT	Data Analyst	150000	USD	150000	US	100	US	M
606	606	2022	MI	FT	AI Scientist	200000	USD	200000	IN	100	US	L

	Unnamed: 0	work_year	experience_level	employment_type	job_title	salary	salary_currency	salary_in_usd	employee_residence	remote_ratio	company_location	company_size
20	20	2020	MI	FT	Machine Learning Engineer	299000	CNY	43331	CN	0	CN	M
21	21	2020	MI	FT	Product Data Analyst	450000	INR	6072	IN	100	IN	L
22	22	2020	SE	FT	Data Engineer	42000	EUR	47899	GR	50	GR	L
23	23	2020	MI	FT	BI Data Analyst	98000	USD	98000	US	0	US	M
24	24	2020	MI	FT	Lead Data Scientist	115000	USD	115000	AE	0	AE	L
25	25	2020	EX	FT	Director of Data Science	325000	USD	325000	US	100	US	L
26	26	2020	EN	FT	Research Scientist	42000	USD	42000	NL	50	NL	L
27	27	2020	SE	FT	Data Engineer	720000	MXN	33511	MX	0	MX	S
28	28	2020	EN	CT	Business Data Analyst	100000	USD	100000	US	100	US	L
29	29	2020	SE	FT	Machine Learning Manager	157000	CAD	117104	CA	50	CA	L
30	30	2020	MI	FT	Data Engineering Manager	51999	EUR	59303	DE	100	DE	S
31	31	2020	EN	FT	Big Data Engineer	70000	USD	70000	US	100	US	L
32	32	2020	SE	FT	Data Scientist	60000	EUR	68428	GR	100	US	L
33	33	2020	MI	FT	Research Scientist	450000	USD	450000	US	0	US	M
34	34	2020	MI	FT	Data Analyst	41000	EUR	46759	FR	50	FR	L
35	35	2020	MI	FT	Data Engineer	65000	EUR	74130	AT	50	AT	L
36	36	2020	MI	FT	Data Science Consultant	103000	USD	103000	US	100	US	L
37	37	2020	EN	FT	Machine Learning Engineer	250000	USD	250000	US	50	US	L
38	38	2020	EN	FT	Data Analyst	10000	USD	10000	NG	100	NG	S
39	39	2020	EN	FT	Machine Learning Engineer	138000	USD	138000	US	100	US	S

	job_title	salary
185	Data Engineer	4000
15	Data Analyst	8000
184	Machine Learning Scientist	12000
192	Big Data Engineer	18000
208	Data Engineer	20000
...	...	...
136	ML Engineer	7000000
137	ML Engineer	8500000
7	Data Scientist	11000000
102	BI Data Analyst	11000000
177	Data Scientist	30400000

	Unnamed: 0	work_year	experience_level	employment_type	job_title	salary	salary_currency	salary_in_usd	employee_residence	remote_ratio	company_location	company_size	salario en pesos
282	282	2021	MI	PT	Data Engineer	59000	EUR	69741	NL	100	NL	L	265500000
226	226	2021	SE	FT	Data Scientist	110000	CAD	87738	CA	100	CA	S	495000000
603	603	2022	SE	FT	Data Engineer	126000	USD	126000	US	100	US	M	567000000
216	216	2021	EN	PT	Computer Vision Engineer	180000	DKK	28609	DK	50	DK	S	810000000
241	241	2021	MI	FT	Data Analyst	80000	USD	80000	US	100	US	L	360000000
...	...	...	...	...	...	...	...	...	...	...	...	...	...
479	479	2022	MI	FT	Data Scientist	120000	USD	120000	US	100	US	M	540000000
403	403	2022	SE	FT	Data Analyst	81666	USD	81666	US	0	US	M	367497000
531	531	2022	MI	FT	Data Analyst	75000	USD	75000	CA	0	CA	M	337500000
431	431	2022	MI	FT	Data Analyst	30000	EUR	32974	ES	100	ES	M	135000000
219	219	2021	SE	FT	Data Analytics Manager	140000	USD	140000	US	100	US	L	630000000

	salary	salary_in_usd	remote_ratio	salario en pesos
0	70000	79833	0	315000000
1	260000	260000	0	1170000000
2	85000	109024	50	382500000
3	20000	20000	0	90000000
4	150000	150000	50	675000000
...	...	...	...	...
602	154000	154000	100	693000000
603	126000	126000	100	567000000
604	129000	129000	0	580500000
605	150000	150000	100	675000000
606	200000	200000	100	900000000

	0	1	2	3	4	5	6	7	8	9	...	40	41	42	43	44	45	46	47	48	49
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
602	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
603	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
604	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
606	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

	job_title_3D Computer Vision Researcher	job_title_AI Scientist	job_title_Analytics Engineer	job_title_Applied Data Scientist	job_title_Applied Machine Learning Scientist	job_title_BI Data Analyst	job_title_Big Data Architect	job_title_Big Data Engineer	job_title_Business Data Analyst	job_title_Cloud Data Engineer	...	job_title_Machine Learning Manager	job_title_Machine Learning Scientist	job_title_Marketing Data Analyst	job_title_NLP Engineer	job_title_Principal Data Analyst	job_title_Principal Data Engineer	job_title_Principal Data Scientist	job_title_Product Data Analyst	job_title_Research Scientist	job_title_Staff Data Scientist
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
602	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
603	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
604	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
606	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

	job_title_3D Computer Vision Researcher	job_title_AI Scientist	job_title_Analytics Engineer	job_title_Applied Data Scientist	job_title_Applied Machine Learning Scientist	job_title_BI Data Analyst	job_title_Big Data Architect	job_title_Big Data Engineer	job_title_Business Data Analyst	job_title_Cloud Data Engineer	...	job_title_Product Data Analyst	job_title_Research Scientist	job_title_Staff Data Scientist	work_year	salary	salary_in_usd	remote_ratio	experiencia_num	tamanio_campania	index_job
job_title_3D Computer Vision Researcher	1.000000	-0.004388	-0.003309	-0.003702	-0.003309	-0.004059	-0.001650	-0.004695	-0.003702	-0.002336	...	-0.002336	-0.006684	-0.001650	-0.023806	0.002001	-0.061243	-0.020895	-0.020805	-0.011777	0.051112
job_title_AI Scientist	-0.004388	1.000000	-0.008797	-0.009844	-0.008797	-0.010792	-0.004388	-0.012483	-0.009844	-0.006210	...	-0.006210	-0.017772	-0.004388	-0.040985	-0.002340	-0.070327	0.020311	-0.114300	-0.054927	0.086976
job_title_Analytics Engineer	-0.003309	-0.008797	1.000000	-0.007423	-0.006633	-0.008138	-0.003309	-0.009412	-0.007423	-0.004683	...	-0.004683	-0.013401	-0.003309	0.070042	-0.007864	0.072030	-0.041894	0.113943	-0.023613	0.250058
job_title_Applied Data Scientist	-0.003702	-0.009844	-0.007423	1.000000	-0.007423	-0.009106	-0.003702	-0.010532	-0.008306	-0.005240	...	-0.005240	-0.014995	-0.003702	0.025662	-0.008954	0.081441	-0.002067	-0.023453	0.113039	0.131184
job_title_Applied Machine Learning Scientist	-0.003309	-0.008797	-0.006633	-0.007423	1.000000	-0.008138	-0.003309	-0.009412	-0.007423	-0.004683	...	-0.004683	-0.013401	-0.003309	0.011156	-0.009641	0.034200	0.033194	-0.067657	0.038704	0.183647
job_title_BI Data Analyst	-0.004059	-0.010792	-0.008138	-0.009106	-0.008138	1.000000	-0.004059	-0.011547	-0.009106	-0.005745	...	-0.005745	-0.016440	-0.004059	-0.082634	0.102181	-0.052908	-0.010454	-0.051174	-0.028968	0.017091
job_title_Big Data Architect	-0.001650	-0.004388	-0.003309	-0.003702	-0.003309	-0.004059	1.000000	-0.004695	-0.003702	-0.002336	...	-0.002336	-0.006684	-0.001650	-0.023806	-0.005239	-0.007216	-0.020895	0.030952	-0.011777	0.117359
job_title_Big Data Engineer	-0.004695	-0.012483	-0.009412	-0.010532	-0.009412	-0.011547	-0.004695	1.000000	-0.010532	-0.006645	...	-0.006645	-0.019015	-0.004695	-0.130391	0.009811	-0.098329	-0.059445	-0.077594	0.010707	-0.084935
job_title_Business Data Analyst	-0.003702	-0.009844	-0.007423	-0.008306	-0.007423	-0.009106	-0.003702	-0.010532	1.000000	-0.005240	...	-0.005240	-0.014995	-0.003702	-0.053407	0.001831	-0.045770	0.042744	-0.093123	0.085147	-0.025695
job_title_Cloud Data Engineer	-0.002336	-0.006210	-0.004683	-0.005240	-0.004683	-0.005745	-0.002336	-0.006645	-0.005240	1.000000	...	-0.003306	-0.009460	-0.002336	-0.033694	-0.006856	0.010015	0.005764	0.007181	-0.016669	0.093180
job_title_Computer Vision Engineer	-0.004059	-0.010792	-0.008138	-0.009106	-0.008138	-0.009983	-0.004059	-0.011547	-0.009106	-0.005745	...	-0.005745	-0.016440	-0.004059	-0.034474	-0.015573	-0.095660	-0.030925	-0.051174	-0.079934	0.089510
job_title_Computer Vision Software Engineer	-0.002863	-0.007612	-0.005740	-0.006423	-0.005740	-0.007042	-0.002863	-0.008145	-0.006423	-0.004052	...	-0.004052	-0.011596	-0.002863	-0.007331	-0.010215	-0.007007	0.050381	-0.095958	-0.092330	0.126986
job_title_Data Analyst	-0.017716	-0.047106	-0.035520	-0.039745	-0.035520	-0.043575	-0.017716	-0.050400	-0.039745	-0.025075	...	-0.025075	-0.071757	-0.017716	0.173510	-0.064268	-0.119363	0.046481	0.040146	-0.092037	-0.201984
job_title_Data Analytics Engineer	-0.003309	-0.008797	-0.006633	-0.007423	-0.006633	-0.008138	-0.003309	-0.009412	-0.007423	-0.004683	...	-0.004683	-0.013401	-0.003309	-0.018287	-0.013842	-0.054565	0.008164	-0.015771	0.038704	0.109858
job_title_Data Analytics Lead	-0.001650	-0.004388	-0.003309	-0.003702	-0.003309	-0.004059	-0.001650	-0.004695	-0.003702	-0.002336	...	-0.002336	-0.006684	-0.001650	0.034934	0.002132	0.167707	0.029039	0.030952	0.050386	0.143121
job_title_Data Analytics Manager	-0.004388	-0.011667	-0.008797	-0.009844	-0.008797	-0.010792	-0.004388	-0.012483	-0.009844	-0.006210	...	-0.006210	-0.017772	-0.004388	0.025951	-0.013780	0.022603	0.039279	0.082300	0.015910	0.253335
job_title_Data Architect	-0.005519	-0.014674	-0.011065	-0.012381	-0.011065	-0.013574	-0.005519	-0.015700	-0.012381	-0.007811	...	-0.007811	-0.022353	-0.005519	0.063256	-0.012865	0.125655	0.097117	0.056306	0.017311	0.355561
job_title_Data Engineer	-0.021414	-0.056939	-0.042935	-0.048043	-0.042935	-0.052672	-0.021414	-0.060922	-0.048043	-0.030309	...	-0.030309	-0.086737	-0.021414	0.141506	-0.049464	0.003176	0.052844	0.030220	0.036617	-0.005350
job_title_Data Engineering Manager	-0.003702	-0.009844	-0.007423	-0.008306	-0.007423	-0.009106	-0.003702	-0.010532	-0.008306	-0.005240	...	-0.005240	-0.014995	-0.003702	-0.106120	-0.012060	0.014049	-0.002067	0.069440	0.057255	0.048616
job_title_Data Science Consultant	-0.004388	-0.011667	-0.008797	-0.009844	-0.008797	-0.010792	-0.004388	-0.012483	-0.009844	-0.006210	...	-0.006210	-0.017772	-0.004388	-0.107922	-0.014090	-0.065322	0.001344	-0.114300	-0.031315	0.008690
job_title_Data Science Engineer	-0.002863	-0.007612	-0.005740	-0.006423	-0.005740	-0.007042	-0.002863	-0.008145	-0.006423	-0.004052	...	-0.004052	-0.011596	-0.002863	-0.007331	-0.010939	-0.036277	0.021503	0.023768	0.051466	0.139756
job_title_Data Science Manager	-0.005769	-0.015339	-0.011567	-0.012943	-0.011567	-0.014190	-0.005769	-0.016412	-0.012943	-0.008165	...	-0.008165	-0.023367	-0.005769	-0.014773	0.067975	0.092202	0.043331	0.078050	0.067487	0.152955
job_title_Data Scientist	-0.022551	-0.059963	-0.045215	-0.050594	-0.045215	-0.055469	-0.022551	-0.064156	-0.050594	-0.031919	...	-0.031919	-0.091343	-0.022551	-0.010968	0.066322	-0.032182	-0.094671	-0.091421	-0.018370	-0.508594
job_title_Data Specialist	-0.001650	-0.004388	-0.003309	-0.003702	-0.003309	-0.004059	-0.001650	-0.004695	-0.003702	-0.002336	...	-0.002336	-0.006684	-0.001650	-0.023806	-0.004186	0.030196	0.029039	0.030952	0.050386	0.102637
job_title_Director of Data Engineering	-0.002336	-0.006210	-0.004683	-0.005240	-0.004683	-0.005745	-0.002336	-0.006645	-0.005240	-0.003306	...	-0.003306	-0.009460	-0.002336	-0.033694	-0.006809	0.036039	0.041102	0.043809	0.027323	0.108807
job_title_Director of Data Science	-0.004388	-0.011667	-0.008797	-0.009844	-0.008797	-0.010792	-0.004388	-0.012483	-0.009844	-0.006210	...	-0.006210	-0.017772	-0.004388	-0.063298	-0.009150	0.126107	-0.074527	0.200259	0.063135	0.028261
job_title_ETL Developer	-0.002336	-0.006210	-0.004683	-0.005240	-0.004683	-0.005745	-0.002336	-0.006645	-0.005240	-0.003306	...	-0.003306	-0.009460	-0.002336	0.049445	-0.010209	-0.046501	-0.100251	-0.029447	-0.016669	0.181734
job_title_Finance Data Analyst	-0.001650	-0.004388	-0.003309	-0.003702	-0.003309	-0.004059	-0.001650	-0.004695	-0.003702	-0.002336	...	-0.002336	-0.006684	-0.001650	-0.023806	-0.007345	-0.028878	-0.020895	0.030952	0.050386	0.109998
job_title_Financial Data Analyst	-0.002336	-0.006210	-0.004683	-0.005240	-0.004683	-0.005745	-0.002336	-0.006645	-0.005240	-0.003306	...	-0.003306	-0.009460	-0.002336	0.007876	-0.001826	0.131945	0.005764	-0.066075	0.071315	0.098389
job_title_Head of Data	-0.003702	-0.009844	-0.007423	-0.008306	-0.007423	-0.009106	-0.003702	-0.010532	-0.008306	-0.005240	...	-0.005240	-0.014995	-0.003702	-0.000695	-0.009899	0.061527	0.042744	0.092663	0.029363	0.106413
job_title_Head of Data Science	-0.003309	-0.008797	-0.006633	-0.007423	-0.006633	-0.008138	-0.003309	-0.009412	-0.007423	-0.004683	...	-0.004683	-0.013401	-0.003309	0.011156	-0.009357	0.039542	-0.041894	0.113943	-0.054771	0.198405
job_title_Head of Machine Learning	-0.001650	-0.004388	-0.003309	-0.003702	-0.003309	-0.004059	-0.001650	-0.004695	-0.003702	-0.002336	...	-0.002336	-0.006684	-0.001650	0.034934	0.149423	-0.019056	-0.020895	0.082709	0.050386	0.132080
job_title_Lead Data Analyst	-0.002863	-0.007612	-0.005740	-0.006423	-0.005740	-0.007042	-0.002863	-0.008145	-0.006423	-0.004052	...	-0.004052	-0.011596	-0.002863	-0.075270	0.011190	-0.019975	0.050381	-0.006164	0.087415	-0.007100
job_title_Lead Data Engineer	-0.004059	-0.010792	-0.008138	-0.009106	-0.008138	-0.009983	-0.004059	-0.011547	-0.009106	-0.005745	...	-0.005745	-0.016440	-0.004059	-0.082634	-0.011893	0.038652	-0.010454	0.076131	-0.105417	-0.019119
job_title_Lead Data Scientist	-0.002863	-0.007612	-0.005740	-0.006423	-0.005740	-0.007042	-0.002863	-0.008145	-0.006423	-0.004052	...	-0.004052	-0.011596	-0.002863	-0.109240	0.035518	0.002875	-0.036251	0.023768	0.015517	-0.026256
job_title_Lead Machine Learning Engineer	-0.001650	-0.004388	-0.003309	-0.003702	-0.003309	-0.004059	-0.001650	-0.004695	-0.003702	-0.002336	...	-0.002336	-0.006684	-0.001650	0.034934	-0.006423	-0.013961	-0.070830	0.030952	-0.011777	0.139441
job_title_ML Engineer	-0.004059	-0.010792	-0.008138	-0.009106	-0.008138	-0.009983	-0.004059	-0.011547	-0.009106	-0.005745	...	-0.005745	-0.016440	-0.004059	-0.058554	0.152338	0.007337	0.030486	-0.072391	-0.079934	0.071405
job_title_Machine Learning Developer	-0.002863	-0.007612	-0.005740	-0.006423	-0.005740	-0.007042	-0.002863	-0.008145	-0.006423	-0.004052	...	-0.004052	-0.011596	-0.002863	0.026638	-0.010231	-0.026280	0.021503	-0.036095	-0.056381	0.152527
job_title_Machine Learning Engineer	-0.010933	-0.029071	-0.021921	-0.024528	-0.021921	-0.026892	-0.010933	-0.031104	-0.024528	-0.015475	...	-0.015475	-0.044284	-0.010933	-0.034325	-0.008945	-0.028159	-0.025471	-0.045843	-0.067984	-0.149037
job_title_Machine Learning Infrastructure Engineer	-0.002863	-0.007612	-0.005740	-0.006423	-0.005740	-0.007042	-0.002863	-0.008145	-0.006423	-0.004052	...	-0.004052	-0.011596	-0.002863	-0.041301	-0.010352	-0.011086	-0.036251	-0.006164	0.015517	0.043980
job_title_Machine Learning Manager	-0.001650	-0.004388	-0.003309	-0.003702	-0.003309	-0.004059	-0.001650	-0.004695	-0.003702	-0.002336	...	-0.002336	-0.006684	-0.001650	-0.082545	-0.004396	0.002754	-0.020895	0.030952	0.050386	0.017989
job_title_Machine Learning Scientist	-0.004695	-0.012483	-0.009412	-0.010532	-0.009412	-0.011547	-0.004695	-0.013356	-0.010532	-0.006645	...	-0.006645	-0.019015	-0.004695	-0.025947	-0.012401	0.075168	-0.006173	-0.022378	0.010707	-0.095405
job_title_Marketing Data Analyst	-0.001650	-0.004388	-0.003309	-0.003702	-0.003309	-0.004059	-0.001650	-0.004695	-0.003702	-0.002336	...	-0.002336	-0.006684	-0.001650	-0.023806	-0.006555	-0.013547	0.029039	0.030952	0.050386	0.062153
job_title_NLP Engineer	-0.001650	-0.004388	-0.003309	-0.003702	-0.003309	-0.004059	-0.001650	-0.004695	-0.003702	-0.002336	...	-0.002336	-0.006684	-0.001650	0.034934	-0.002211	-0.043008	-0.020895	-0.020805	0.050386	0.135760
job_title_Principal Data Analyst	-0.002336	-0.006210	-0.004683	-0.005240	-0.004683	-0.005745	-0.002336	-0.006645	-0.005240	-0.003306	...	-0.003306	-0.009460	-0.002336	0.007876	-0.007508	0.008274	0.041102	0.007181	-0.060661	0.160898
job_title_Principal Data Engineer	-0.002863	-0.007612	-0.005740	-0.006423	-0.005740	-0.007042	-0.002863	-0.008145	-0.006423	-0.004052	...	-0.004052	-0.011596	-0.002863	-0.041301	0.000198	0.214748	0.050381	0.083630	0.051466	0.146142
job_title_Principal Data Scientist	-0.004388	-0.011667	-0.008797	-0.009844	-0.008797	-0.010792	-0.004388	-0.012483	-0.009844	-0.006210	...	-0.006210	-0.017772	-0.004388	-0.063298	-0.008210	0.156833	0.039279	0.082300	0.015910	0.106548
job_title_Product Data Analyst	-0.002336	-0.006210	-0.004683	-0.005240	-0.004683	-0.005745	-0.002336	-0.006645	-0.005240	-0.003306	...	1.000000	-0.009460	-0.002336	-0.116833	-0.003316	-0.080497	-0.029575	-0.029447	-0.016669	-0.037047
job_title_Research Scientist	-0.006684	-0.017772	-0.013401	-0.014995	-0.013401	-0.016440	-0.006684	-0.019015	-0.014995	-0.009460	...	-0.009460	1.000000	-0.006684	-0.066683	-0.022766	-0.007608	-0.071993	-0.071168	0.093927	0.057958
job_title_Staff Data Scientist	-0.001650	-0.004388	-0.003309	-0.003702	-0.003309	-0.004059	-0.001650	-0.004695	-0.003702	-0.002336	...	-0.002336	-0.006684	1.000000	-0.023806	-0.005765	-0.004181	0.029039	0.030952	-0.011777	0.121039
work_year	-0.023806	-0.040985	0.070042	0.025662	0.011156	-0.082634	-0.023806	-0.130391	-0.053407	-0.033694	...	-0.116833	-0.066683	-0.023806	1.000000	-0.087577	0.170493	0.076314	0.294759	-0.078764	0.024699
salary	0.002001	-0.002340	-0.007864	-0.008954	-0.009641	0.102181	-0.005239	0.009811	0.001831	-0.006856	...	-0.003316	-0.022766	-0.005765	-0.087577	1.000000	-0.083906	-0.014608	-0.027517	0.079959	-0.006517
salary_in_usd	-0.061243	-0.070327	0.072030	0.081441	0.034200	-0.052908	-0.007216	-0.098329	-0.045770	0.010015	...	-0.080497	-0.007608	-0.004181	0.170493	-0.083906	1.000000	0.132122	0.484233	0.151205	0.192384
remote_ratio	-0.020895	0.020311	-0.041894	-0.002067	0.033194	-0.010454	-0.020895	-0.059445	0.042744	0.005764	...	-0.029575	-0.071993	0.029039	0.076314	-0.014608	0.132122	1.000000	0.097784	-0.022070	0.083397
experiencia_num	-0.020805	-0.114300	0.113943	-0.023453	-0.067657	-0.051174	0.030952	-0.077594	-0.093123	0.007181	...	-0.029447	-0.071168	0.030952	0.294759	-0.027517	0.484233	0.097784	1.000000	0.063511	0.157207
tamanio_campania	-0.011777	-0.054927	-0.023613	0.113039	0.038704	-0.028968	-0.011777	0.010707	0.085147	-0.016669	...	-0.016669	0.093927	-0.011777	-0.078764	0.079959	0.151205	-0.022070	0.063511	1.000000	0.076542
index_job	0.051112	0.086976	0.250058	0.131184	0.183647	0.017091	0.117359	-0.084935	-0.025695	0.093180	...	-0.037047	0.057958	0.121039	0.024699	-0.006517	0.192384	0.083397	0.157207	0.076542	1.000000

	company_location_AE	company_location_AS	company_location_AT	company_location_AU	company_location_BE	company_location_BR	company_location_CA	company_location_CH	company_location_CL	company_location_CN	...	company_location_PL	company_location_PT	company_location_RO	company_location_RU	company_location_SG	company_location_SI	company_location_TR	company_location_UA	company_location_US	company_location_VN
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
602	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
603	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
604	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
606	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0

	nombres	edad
0	ana	12
1	juana	23
2	sara	34

	nombres	salario
0	ana	120
1	juana	230
2	sara	340

	nombres	edad	salario
0	ana	12	120
1	juana	23	230
2	sara	34	340

	0	1	2	3	4	5	6	7	8	9	...	40	41	42	43	44	45	46	47	48	49
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
602	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
603	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
604	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
606	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

	job_title_3D Computer Vision Researcher	job_title_AI Scientist	job_title_Analytics Engineer	job_title_Applied Data Scientist	job_title_Applied Machine Learning Scientist	job_title_BI Data Analyst	job_title_Big Data Architect	job_title_Big Data Engineer	job_title_Business Data Analyst	job_title_Cloud Data Engineer	...	job_title_Machine Learning Manager	job_title_Machine Learning Scientist	job_title_Marketing Data Analyst	job_title_NLP Engineer	job_title_Principal Data Analyst	job_title_Principal Data Engineer	job_title_Principal Data Scientist	job_title_Product Data Analyst	job_title_Research Scientist	job_title_Staff Data Scientist
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
602	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
603	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
604	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
606	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

	company_location_AE	company_location_AS	company_location_AT	company_location_AU	company_location_BE	company_location_BR	company_location_CA	company_location_CH	company_location_CL	company_location_CN	...	company_location_PL	company_location_PT	company_location_RO	company_location_RU	company_location_SG	company_location_SI	company_location_TR	company_location_UA	company_location_US	company_location_VN
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
602	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
603	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
604	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
606	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0

	company_location_AE	company_location_AS	company_location_AT	company_location_AU	company_location_BE	company_location_BR	company_location_CA	company_location_CH	company_location_CL	company_location_CN	...	job_title_Machine Learning Manager	job_title_Machine Learning Scientist	job_title_Marketing Data Analyst	job_title_NLP Engineer	job_title_Principal Data Analyst	job_title_Principal Data Engineer	job_title_Principal Data Scientist	job_title_Product Data Analyst	job_title_Research Scientist	job_title_Staff Data Scientist
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
602	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
603	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
604	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
606	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

	0	1	2	3	4	5	6	7	8	9	...	40	41	42	43	44	45	46	47	48	49
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
602	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
603	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
604	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
606	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

	job_title_3D Computer Vision Researcher	job_title_AI Scientist	job_title_Analytics Engineer	job_title_Applied Data Scientist	job_title_Applied Machine Learning Scientist	job_title_BI Data Analyst	job_title_Big Data Architect	job_title_Big Data Engineer	job_title_Business Data Analyst	job_title_Cloud Data Engineer	...	job_title_Machine Learning Manager	job_title_Machine Learning Scientist	job_title_Marketing Data Analyst	job_title_NLP Engineer	job_title_Principal Data Analyst	job_title_Principal Data Engineer	job_title_Principal Data Scientist	job_title_Product Data Analyst	job_title_Research Scientist	job_title_Staff Data Scientist
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
602	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
603	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
604	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
606	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

	company_location_AE	company_location_AS	company_location_AT	company_location_AU	company_location_BE	company_location_BR	company_location_CA	company_location_CH	company_location_CL	company_location_CN	...	company_location_PL	company_location_PT	company_location_RO	company_location_RU	company_location_SG	company_location_SI	company_location_TR	company_location_UA	company_location_US	company_location_VN
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
602	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
603	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
604	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0
606	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0

	company_location_AE	company_location_AS	company_location_AT	company_location_AU	company_location_BE	company_location_BR	company_location_CA	company_location_CH	company_location_CL	company_location_CN	...	job_title_Machine Learning Manager	job_title_Machine Learning Scientist	job_title_Marketing Data Analyst	job_title_NLP Engineer	job_title_Principal Data Analyst	job_title_Principal Data Engineer	job_title_Principal Data Scientist	job_title_Product Data Analyst	job_title_Research Scientist	job_title_Staff Data Scientist
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
602	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
603	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
604	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
606	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0